The old thimble and pea prestidigitation ...
BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
BrainChip is the worldwide leader in on-chip edge AI processing and learning technology, that enables faster, efficient, secure, and customizable intelligent devices untethered from the cloud. The company’s first-to-market neuromorphic processor, AkidaTM, mimics the human brain, the most efficient computer known, to analyze only essential sensor inputs at the point of acquisition, executing only necessary operations and therefore, processing data with unparalleled efficiency and precision. This supports a distributed intelligence approach keeping machine learning local to the chip, independent of the cloud, dramatically reducing latency, while simultaneously improving privacy and data security.
The Akida neural processor is designed to provide a complete ultra-low power Edge AI network processor for vision, audio, smart transducers, vital signs and, broadly, any sensor application.
BrainChip’s scalable solutions, that can be used standalone or integrated into systems on chip to execute today’s models and future networks directly in hardware, empowering the market to create much more intelligent, cost-effective devices and services universally deployable across real-world applications in connected cars, healthcare, consumer electronics, industrial IoT, smart-agriculture and more, including use in a space mission and the most stringent conditions.
BrainChip is the foundation for cost-effective, fan-less, portable, real-time Edge AI systems that can offload the cloud, reducing the rapid growth in carbon footprint of datacenters. In addition, Akida’s unique capability to learn locally on device also reduces retraining of models in the cloud whose skyrocketing cost is a barrier to the growth of AIoT.
www.tinyml.org
The Akida neural processor is designed to provide a complete ultra-low power Edge AI network processor for vision, audio, smart transducers, vital signs and, broadly, any sensor application.
BrainChip’s scalable solutions, that can be used standalone or integrated into systems on chip to execute today’s models and future networks directly in hardware, empowering the market to create much more intelligent, cost-effective devices and services universally deployable across real-world applications in connected cars, healthcare, consumer electronics, industrial IoT, smart-agriculture and more, including use in a space mission and the most stringent conditions.
BrainChip is the foundation for cost-effective, fan-less, portable, real-time Edge AI systems that can offload the cloud, reducing the rapid growth in carbon footprint of datacenters. In addition, Akida’s unique capability to learn locally on device also reduces retraining of models in the cloud whose skyrocketing cost is a barrier to the growth of AIoT.
Sponsors | tinyML Foundation
TinyML Summit. The topic is advances in ultra-low power Machine Learning technologies and applications.
I met @OutbackJohn at a Melbourne shareholder catch up a few years ago. I can vouch that he is a LTH and the real deal. Good on you Outback for making it up to Sydney.
Unfortunately the roll out of my new clinic has clashed with the AGM. Enjoy all that are attending and I’ll be sure to be signing in live on Tuesday. The plan is to be at the next one and we will hopefully be chatting about how great it is to have some consistent revenue flying in!
Edit: have now seen that @JoMo68 has also spoken for Outback…also met JoMo at this same event. Bring on the next $1 party event in the best city in Australia
Last edited:
OutbackJohn
Member
If you’re implying that Outbackjohn is a blow in, he is definitely not - he is one of the longtermers from the old site. Had the pleasure of meeting him at our Melbourne $1 party (that feels like a while ago)
It's nice to be validated as a real person. Thank you both!I met @OutbackJohn at a Melbourne shareholder catch up a few years ago. I can vouch that he is a LTH and the real deal. Good on you Outback for making it up to Sydney.
Unfortunately the roll out of my new clinic has clashed with the AGM. Enjoy all that are attending and I’ll be sure to be signing in live on Tuesday. The plan is to be at the next one and we will hopefully be chatting about how great it is to have some consistent revenue flying in!
Edit: have now seen that @JoMo68 has also spoken for Outback…also met JoMo at this same event. Bring on the next $1 party event in the best city in Australia
MDhere
Top 20
dittoI met @OutbackJohn at a Melbourne shareholder catch up a few years ago. I can vouch that he is a LTH and the real deal. Good on you Outback for making it up to Sydney.
Unfortunately the roll out of my new clinic has clashed with the AGM. Enjoy all that are attending and I’ll be sure to be signing in live on Tuesday. The plan is to be at the next one and we will hopefully be chatting about how great it is to have some consistent revenue flying in!
Edit: have now seen that @JoMo68 has also spoken for Outback…also met JoMo at this same event. Bring on the next $1 party event in the best city in Australia
cosors
👀
I love this and wish I wouldn't be so infinitely far away from you
@Rocket577
____
To anticipate Dredd I don't think this is or can be against our rules.
Last edited:
Australia-United States Joint Leaders’ Statement - An Alliance for our Times | The White House
We, Prime Minister Albanese and President Biden, meet at a uniquely consequential time for our Alliance, the Indo-Pacific, and the world. Our partnership
MDhere
Top 20
See you at the agm to some of the Melbourne crew that i met on my trip and last years agm attendees. Plate of hot chips will be at whatever table we get to after agm. To the rest of the Tse group, will have a cheers for you too.
Despite all the questions, I trust the behind the scenes hard work of Brainchip staff so I have NO doubt.
Happy Monday fellow brners
Despite all the questions, I trust the behind the scenes hard work of Brainchip staff so I have NO doubt.
Happy Monday fellow brners
chapman89
Founding Member
I’ll be meeting with a few shareholders in the morning around 9am in the city for a coffee.See you at the agm to some of the Melbourne crew that i met on my trip and last years agm attendees. Plate of hot chips will be at whatever table we get to after agm. To the rest of the Tse group, will have a cheers for you too.
Despite all the questions, I trust the behind the scenes hard work of Brainchip staff so I have NO doubt.
Happy Monday fellow brners
Others are welcome to join.
The AGM will be great, tough questions the company will face regarding communicating partnerships better and how they plan to address this moving forward.
Other than the what or what not to announce on the asx I am very happy and confident than I’ve ever been with the company.
Come on guys we’ve got renesas taping out the worlds first MCU’s containing akida IP, this is not only exciting but it’s what we’ve been waiting for and this will really shine the light on us.
I could go on and on but I’ll leave it for the company to address tomorrow.
I am very impressed with your take on BRN things as they currently stand.
Labsy
Regular
How will other technologies overtake us? You should work for Intel, they need your help desperately o wise one...
Good morning all,
Oh to be that fly and only fly on the wall at a certain meeting that's underway now in Sydney, will an announcement be released
this morning ? I'm still betting on no...happy to end up with egg on my face though !
Very busy few days ahead for Peter and the team currently here in Australia.
Here's to a positive week ahead...cheers
Tech.
Oh to be that fly and only fly on the wall at a certain meeting that's underway now in Sydney, will an announcement be released
this morning ? I'm still betting on no...happy to end up with egg on my face though !
Very busy few days ahead for Peter and the team currently here in Australia.
Here's to a positive week ahead...cheers
Tech.
Damo4
Regular
How long have you been on the board of directors?
Or are you Peter?
Surely you wouldn't be posting unsubstantiated information and must be in the know.
rgupta
Regular
You are right on point. Technology can become obsolete in no time. But you forget to mention each technology have to go through rigorous checks before being adopted. Any new technology have to pass through the same tests what brn is going through.
There are still a chances of failure but chances are becoming less and less with each passing day.
Do your own research.
Dhm
Regular
Regarding the AFR article that mentions BRN in a somewhat disparaging way, I emailed Mr. Pollak inviting him to the AGM. I was somewhat cheeky with the ‘informed’ comment, but I didn’t want to sound like a peeved shareholder. I doubt He will come, but you can only do your best.
The measure of intelligence is the ability to change.
BTW did any of you guys watch the US PGA this morning? Wasn’t Michael Block just brilliant! It just shows that golf can be an everyman sport! I bet you were watching @TECH and @Violin1
The measure of intelligence is the ability to change.
BTW did any of you guys watch the US PGA this morning? Wasn’t Michael Block just brilliant! It just shows that golf can be an everyman sport! I bet you were watching @TECH and @Violin1
Last edited:
buena suerte :-)
BOB Bank of Brainchip
Wasn’t Michael Block just brilliant! ..... Absolutely!.. A great guy ... A much needed breath of fresh air to give the game a good feel story with all the other s*** that is going on!
Great letter/invite
Hope all that are attending the AGM have a great time with Q&A's, meeting our great team and catching up with fellow Shareholders for a few
.
Bravo
If ARM was an arm, BRN would be its biceps💪!
I luuuurrrvee it! Mercedes-Benz team trains a quantized long short-term memory (LSTM) neural network...
Automated workflow for deploying virtual sensors to powertrain ECU.
Many automotive manufacturers equip their development cars with numerous additional hardware sensors to gather data for diagnosing issues and refining the design. Once the car transitions to production, many of these sensors are removed to reduce costs. In some cases, however, the hardware sensors can be replaced with virtual sensors, which are cheaper software alternatives that can further improve safety, efficiency, and driver comfort.
Mercedes-Benz recently used MATLAB® and Simulink® to establish a new workflow for deploying virtual sensors, such as those that simulate the functionality of a piston pressure sensor. These sensors are based on deep learning networks designed to run on resource-limited ECU microcontrollers. This automated workflow replaced a manual workflow that was both slower and relied on a trial-and-error approach.
“The MathWorks team helped us develop an easy-to-use pipeline for creating and integrating neural networks into our vehicle controller units,” says Katja Deuschl, AI developer at Mercedes-Benz. “With this pipeline, we are now able to create and deploy different types of neural networks for virtual sensors and a variety of other applications.”
To run models based on these frameworks on an ECU, developers must first translate the Python® code to C and transform the model parameters and calculations into fixed point operations. This process took Mercedes-Benz weeks to complete, produced unreliable results, and was difficult to teach to new team members.
As they worked through the many manual steps needed to translate the model from Python, the team had to ensure that the model implemented in C would fit within the limited memory space of the ECU and would run fast enough to provide real-time inference for time-sensitive operations such as sensing piston pressure. The team wanted to establish a more reliable and more automated process.
In this workflow, the Mercedes-Benz team trains a quantized long short-term memory (LSTM) neural network in Python using the QKeras library.
They use Deep Learning Toolbox™ to import the trained network into MATLAB. They then run a custom MATLAB script to convert the imported neural network into a Simulink model.
Next, the team uses Fixed-Point Designer™ to convert all parameters in the model from floating-point to fixed-point data types in preparation for deployment to an automotive ECU.
After verifying the fixed-point model via simulation in Simulink, the team hands the model off to a third-party software integrator, who implements it on the ECU with other software components.
Having successfully implemented its first use case—a virtual sensor for piston pressure—with this workflow, the Mercedes-Benz team is now applying the same process to additional sensors and other deep learning applications for ECU targets.
www.mathworks.com
Mercedes-Benz team trains a quantized long short-term memory (LSTM) neural network...Mercedes-Benz Simulates Hardware Sensors with Deep Neural Networks
Challenge
Simulate automotive hardware sensors with deep neural networks.Solution
Use MATLAB, Simulink, Deep Learning Toolbox, and Fixed-Point Designer to convert QKeras deep learning models into code that can be deployed to an automotive ECU.Results
- CPU, memory, and performance requirements met
- Flexible process established
- Development speed increased 600%
Automated workflow for deploying virtual sensors to powertrain ECU.
Many automotive manufacturers equip their development cars with numerous additional hardware sensors to gather data for diagnosing issues and refining the design. Once the car transitions to production, many of these sensors are removed to reduce costs. In some cases, however, the hardware sensors can be replaced with virtual sensors, which are cheaper software alternatives that can further improve safety, efficiency, and driver comfort.
Mercedes-Benz recently used MATLAB® and Simulink® to establish a new workflow for deploying virtual sensors, such as those that simulate the functionality of a piston pressure sensor. These sensors are based on deep learning networks designed to run on resource-limited ECU microcontrollers. This automated workflow replaced a manual workflow that was both slower and relied on a trial-and-error approach.
“The MathWorks team helped us develop an easy-to-use pipeline for creating and integrating neural networks into our vehicle controller units,” says Katja Deuschl, AI developer at Mercedes-Benz. “With this pipeline, we are now able to create and deploy different types of neural networks for virtual sensors and a variety of other applications.”
Challenge
Most deep neural networks are designed to run on computers with significantly more processing power and memory capacity than an automotive ECU. Moreover, ECUs don’t support commonly used deep learning frameworks—such as TensorFlow™ and PyTorch®—or the floating-point operations they require.To run models based on these frameworks on an ECU, developers must first translate the Python® code to C and transform the model parameters and calculations into fixed point operations. This process took Mercedes-Benz weeks to complete, produced unreliable results, and was difficult to teach to new team members.
As they worked through the many manual steps needed to translate the model from Python, the team had to ensure that the model implemented in C would fit within the limited memory space of the ECU and would run fast enough to provide real-time inference for time-sensitive operations such as sensing piston pressure. The team wanted to establish a more reliable and more automated process.
Solution
The Mercedes-Benz team worked with MathWorks engineers to implement an optimized workflow to convert Python deep learning models into code and parameters that can be transferred to their ECU integration pipeline.In this workflow, the Mercedes-Benz team trains a quantized long short-term memory (LSTM) neural network in Python using the QKeras library.
They use Deep Learning Toolbox™ to import the trained network into MATLAB. They then run a custom MATLAB script to convert the imported neural network into a Simulink model.
Next, the team uses Fixed-Point Designer™ to convert all parameters in the model from floating-point to fixed-point data types in preparation for deployment to an automotive ECU.
After verifying the fixed-point model via simulation in Simulink, the team hands the model off to a third-party software integrator, who implements it on the ECU with other software components.
Having successfully implemented its first use case—a virtual sensor for piston pressure—with this workflow, the Mercedes-Benz team is now applying the same process to additional sensors and other deep learning applications for ECU targets.
Results
- CPU, memory, and performance requirements met. “With MATLAB and Simulink, we implemented a virtual sensor neural network that fits on the ECU and meets our benchmark requirements,” Deuschl says. “We would not have been able to produce a similar virtual sensor with classic software development.”
- Flexible process established. “We are already using the automated workflow we created with MATLAB and Simulink for other use cases,” says Deuschl. “We made small adaptations to support deployment on two different powertrain controllers, and the workflow is also applicable to other types of deep learning models such as gated recurrent units and fully-connected neural networks.”
- Development speed increased 600%. “With Deep Learning Toolbox and Fixed-Point Designer, we improved development speed by about six times compared to our previous manual development process,” Deuschl says. “And with less manual development, we committed fewer errors in creating the model and the code.”
Mercedes-Benz Simulates Hardware Sensors with Deep Neural Networks
Mercedes-Benz used Deep Learning Toolbox and Fixed-Point Designer to create a pipeline for deploying neural networks created and trained in Python to automotive ECUs.
Last edited:
Similar threads
